Comparison of semiparametric and parametric methods for estimating copulas

Kim, Gunky; Silvapulle, Mervyn J.; Silvapulle, Paramsothy

doi:10.1016/j.csda.2006.10.009

Cited by 273 publications

(154 citation statements)

References 13 publications

Supporting

Mentioning

148

Contrasting

Unclassified

Order By: Relevance

“…Each marginal distribution is estimated nonparametrically by the empirical distribution function, thus allowing the distribution of the marginals to be not restricted by parametric families. Kim et al (2007aKim et al ( , 2008 have shown that the semi parametric method implemented in our study is robust when the margins are misspecified and as efficient as MLE in moderate sample sizes (greater than 100). As financial markets provide high-frequency data with large sample sizes, semi-parametric methods provide an attractive approach to investigate the dependence structure in the exchange rate returns.…”

Section: Fully Parametric Estimation Methods Such As Inference Functimentioning

confidence: 99%

See 1 more Smart Citation

Modelling the bivariate dependence structure of exchange rates before and after the introduction of the euro: a semi-parametric approach

2010

View full text Add to dashboard Cite

This paper investigates the bivariate dependence structure for three pairs of exchange rates measured against the US dollar: Euro and Japanese yen, Euro and British pound, Euro and Swiss franc, over the period January 1994 to November 2007. The Deutsche mark (DM) is used for the pre-euro period. By using non-parametric plots and copula models estimated by semi-parametric methods, we are able to detect changes in the dependence structure from the pre-euro to the post-euro period for the pairs DM (Euro)-Japanese yen, and DM (Euro)-British pound, with major changes occurring during the initial years of the launch of the new currency. For these two pairs of exchange rates we also capture asymmetric tail dependence, implying different degrees of comovements during appreciations and depreciations against the dollar. The dependence between the DM (Euro) and the Swiss franc remains unchanged, both in strength and structure, over the whole sample period, reflecting a marked tendency of the Swiss franc to follow the fluctuations of the DM and Euro against the dollar. The results may be of interest for international trade, international portfolio diversification and currency risk management.

show abstract

Section: Fully Parametric Estimation Methods Such As Inference Functimentioning

confidence: 99%

“…Since our interest is in conducting statistical inference on copula and tail dependence parameters, the use of parametric copulas would permit this (see Kim et al 2007a). …”

Section: Semi-parametric Estimation Of Copulasmentioning

confidence: 99%

Modelling the bivariate dependence structure of exchange rates before and after the introduction of the euro: a semi-parametric approach

2010

View full text Add to dashboard Cite

show abstract

“…In general, it is possible to estimate the copula and marginals parameters together in one step using the so-called full Maximum Likelihood Estimation; see for instance Kim et al (2007). However, this "aggregated" estimation approach can become too complex to formulate and to effectively solve in most cases.…”

Section: Estimation Of Copulasmentioning

confidence: 99%

Comparison of different copula assumptions and their application in portfolio construction

Štulajter¹

2009

ER-CEREI

View full text Add to dashboard Cite

The paper deals with modeling of mutual dependencies among financial assets. Its aim is to investigate the impact of different copula assumptions on optimal portfolios, when CVaR optimization is used. Strategic asset allocation perspective is supposed. It is demonstrated that copula functions enable us to separate the modeling of dependency features of financial assets from the modeling of marginal distribution characteristics, in the context of practical portfolio construction tasks. The difference between portfolios constructed using normal copula and student t copula is shown when mutual or pension fund exposed to long-only constrain is assumed. The fund is considered to invest solely into equity and fixed-income instruments. As expected, the exclusive use of linear correlation coefficients leads to underestimation of total portfolio risk. The superiority of student t copula portfolios intensifies as the confidence level of CVaR rises and/or as the CVaR target increases.

show abstract

“…7 Note that the CML estimator has been shown to yield less biased parameter estimates than, e.g., the Inference For Margins or Full Maximum-Likelihood methods (Kim et al, 2007). It has since been accepted as the method of choice for estimating copula parameters (Genest et al, 2009).…”

Section: Value-at-risk Forecastingmentioning

confidence: 99%

“…1 We compare our proposed method to a conventional copula-GARCH model where the parameter of the Clayton copula is estimated via Canonical Maximum-Likelihood (CML) (Kim et al, 2007). We examine the usefulness of our method by analyzing a data sample of nine different portfolios consisting of different financial assets.…”

Section: Introductionmentioning

confidence: 99%

Forecasting portfolio-Value-at-Risk with nonparametric lower tail dependence estimates

Siburg¹,

Stoimenov²,

Weiß³

2015

Journal of Banking & Finance

View full text Add to dashboard Cite

We propose to forecast the Value-at-Risk of bivariate portfolios using copulas which are calibrated on the basis of nonparametric sample estimates of the coefficient of lower tail dependence. We compare our proposed method to a conventional copula-GARCH model where the parameter of a Clayton copula is estimated via Canonical Maximum-Likelihood. The superiority of our proposed model is exemplified by analyzing a data sample of nine different financial portfolios. A comparison of the out-of-sample forecasting accuracy of both models confirms that our model yields economically significantly better Value-at-Risk forecasts than the competing parametric calibration strategy.

show abstract

Comparison of semiparametric and parametric methods for estimating copulas

Cited by 273 publications

References 13 publications

Modelling the bivariate dependence structure of exchange rates before and after the introduction of the euro: a semi-parametric approach

Modelling the bivariate dependence structure of exchange rates before and after the introduction of the euro: a semi-parametric approach

Comparison of different copula assumptions and their application in portfolio construction

Forecasting portfolio-Value-at-Risk with nonparametric lower tail dependence estimates

Contact Info

Product

Resources

About